Model rankings

526 models · 3 boards · 2 sources

Week of September 8, 2025

October 20, 20252 changes October 13, 202518 changes October 6, 20257 changes September 29, 202516 changes September 22, 20258 changes September 15, 20251 change September 8, 202513 changes September 1, 20253 changes August 25, 202519 changes August 18, 20255 changes August 11, 202524 changes August 4, 20259 changes

Artificial AnalysisText-to-video arenaArenaText-to-video arena

Text-to-video arena · Anonymous head-to-head votes · Published September 8, 2025

Best video

veo-3-fast-audioGoogle1,396Score

Best open model

wan-v2.2-a14bAlibaba1,144Score

Best from China

hailuo-02-proMiniMax1,255Score

Most voted

veo-3-fast-audioGoogle10,313Votes

Top three by Score

1veo-3-fast-audioGoogle1,396

2veo-3-audioGoogle1,393

3veo-3-fastGoogle1,292

Top three open models

1wan-v2.2-a14bAlibaba · #10 overall1,144

2mochi-v1Genmo · #15 overall1,002

This week's changes

Grok Code Fast 1Intelligence · #22New

Qwen3 Max (Preview)Intelligence · #23New

Hermes 4 - Llama-3.1 405B (Reasoning)Intelligence · #40New

Hermes 4 - Llama-3.1 70B (Reasoning)Intelligence · #45New

Kimi K2 0905Intelligence · #19Up 12

All Open Closed

All regions US China

One row per model All variants

SortScore Votes

Rank	Change	Model	Score	95% interval	Votes
1	—	veo-3-fast-audioClosedGoogle	1,396	±10	10,313
2	—	veo-3-audioClosedGoogle	1,393	±10	7,443
3	—	veo-3-fastClosedGoogle	1,292	±10	5,931
4	—	veo-3ClosedGoogle	1,286	±10	5,719
5	—	veo-2ClosedGoogle	1,189	±10	5,637
6	—	soraClosedOpenAI	1,093	±12	3,082
7	—	ray2ClosedLuma AI	1,079	±10	4,296
8	—	pika-v2.2ClosedPika	1,007	±12	4,706

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026

64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi